# AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation

arXiv: https://arxiv.org/abs/2607.04303 · HTML: https://mlsanity.com/paper/2607.04303/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 69 references that are in the map.
- First posted on arXiv 5 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline](https://mlsanity.com/paper/2312.00343/) (2023)
- [StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes](https://mlsanity.com/paper/2509.16415/) (2025)
- [UWStereo: A Large Synthetic Dataset for Underwater Stereo Matching](https://mlsanity.com/paper/2409.01782/) (2024)
- [Stereo Anything: Unifying Zero-shot Stereo Matching with Large-Scale Mixed Data](https://mlsanity.com/paper/2411.14053/) (2024)
- [Boosting Zero-shot Stereo Matching using Large-scale Mixed Images Sources in the Real World](https://mlsanity.com/paper/2505.08607/) (2025)

## Built on by (most cited first, 1 of 1)

- [GeoStereo: A Unified Stereo Geometry Estimation Framework for Disparity and Surface Normal](https://mlsanity.com/paper/2607.24024/) (2026)

## Abstract (arXiv)

Learning-based stereo matching models struggle in underwater environments due to scarce in-domain data and the difficulty of extracting discriminative correspondences from degraded imagery. In this work, we present AquaStereo, a perception-enhanced framework with a data simulation pipeline and a self-distillation strategy that jointly address data scarcity and feature degradation in underwater stereo matching. First, a depth-conditioned diffusion pipeline renders underwater stereo pairs while preserving binocular geometry, with a lightweight left-right consistency module ensuring geometric alignment. Training on this synthetic corpus effectively narrows the terrestrial-underwater gap and improves zero-shot robustness. Second, a frozen binocular teacher trained on clean terrestrial pairs guides a student exposed to rendered underwater pairs with perturbations. A stage-weighted sequence loss is performed to align the student's disparities with the teacher's geometry, while a clean-branch supervision with shared pseudo targets prevents scale drift. To further enhance feature stability under turbidity and low texture, we introduce learnable perception frames, a perception-enhanced feature formulation that constructs robust matching descriptors by fusing temporal cues from two auxiliary views encoded by a video backbone with semantic features extracted by a strong image encoder. Extensive experiments demonstrate that AquaStereo substantially improves robustness and zero-shot generalization in challenging underwater scenarios. The code is available at https://github.com/qz-wei/AquaStereo.